Convolutional Neural Network on Tanned and Synthetic Leather Textures

Tanned leather is an output from complex processes called tanning. Leather tanning is an important step that used to protect the fiber or protein structure of animal’s skin. Another reason of tanning process is to prevent the animal’s skin from any defect or rot. After the tanning is complete, the leather can be applied to produce a wide variety of leather products. Thus, the leather prices usually more expensive because it takes longer time in process. Another way to get cheaper price is make non-animal leather that usually known as synthetic or imitation leather. The purpose of this paper is to classify the tanned leather and synthetic leather by using Convolutional Neural Network (CNN). The tanned leather consist of cow, goat and sheep leathers. The proposed method will classify into four class, they are cow, goat, sheep and synthetic leathers. This research consist of 1280 training data with 448×448 pixels size as the input. With CNN method, this research shows a good result for the accuracy about 92.1%.